Famulor administration spans many connected tools, records, and sensitive actions. This skill guides Claude, Codex, and Claude Code through scoped MCP operations with authorization checks.

Long-running web operations can feel stalled and cause users to abandon important tasks. This skill captures timed states, evaluates waiting feedback, and produces prioritized improvements.

Claude Code forgets your corrections between sessions, so you repeat the same guidance again and again. claude-reflect captures those corrections automatically and lets you review and apply them to your CLAUDE.md memory files with one command.

Annual goals often lack actionable daily steps. This skill converts one outcome into quarterly milestones, weekly process goals, and daily checklists.

Data teams need a safer way to load S3 files into Bauplan without changing main immediately. This skill guides a branch-based Write-Audit-Publish flow with checks before publish.

Bauplan projects need clear DAG structure, branch safety, and consistent SQL or Python model patterns. This skill guides Claude, Codex, and Claude Code through pipeline files, validation, and safe run workflows.

Teams often need quick visual assets without leaving their AI workflow. This skill turns prompts and selected images into Gemini generated files for design, documentation, and product work.

Visual issues are easy to miss when an AI creates pages, documents, or presentations. This skill captures previews, checks design details, and guides focused fixes.

Vague requests create missed details, weak acceptance criteria, and unclear execution. This skill turns them into structured specifications with assumptions, constraints, priorities, and next steps.

Validation bugs create weak application boundaries and unclear user errors. This skill gives practical Zod patterns for TypeScript schemas, API validation, transforms, and typed results.

Voice changes can break echo cancellation, WebRTC flow, or OpenAI Realtime API behavior. This skill guides Quetrex changes using documented architecture constraints and review checks.

Strict TypeScript projects fail when weak typing enters reviews or generated code. This skill gives Claude, Codex, and Claude Code clear patterns for safer TypeScript output.

TypeScript projects can drift into unsafe patterns that hide runtime defects. This skill guides Claude, Codex, and Claude Code toward stricter type usage, clearer errors, and safer narrowing.

Teams often skip tests or write them after implementation. This skill guides Claude, Codex, and Claude Code through test-first delivery.

React teams need consistent ShadCN patterns for forms, dialogs, tables, and accessible controls. This skill guides Claude, Codex, and Claude Code toward Radix components, Tailwind utilities, and validation practices.

Teams need consistent UI patterns without rebuilding common animations. This skill provides ShadCN and Framer Motion examples for cards, lists, dialogs, transitions, and loading states.

Large repositories make concept-based code discovery slow and expensive. This skill guides Claude, Codex, and Claude Code to use Serena MCP for targeted symbol search.

Security-sensitive code is easy to ship with hidden flaws in authentication, input handling, and secrets. This skill gives Claude, Codex, and Claude Code structured security references and scanner guidance for safer reviews.

Building Redis-backed features can be error-prone. This skill provides Upstash Redis patterns for caching, invalidation, rate limiting, sessions, pub/sub, and leaderboards.

Context loss can interrupt active work and hide the next action. This skill rebuilds session state from memory-keeper checkpoints.